How do I connect my MCP client to Mnemom?
Add a custom MCP connector pointing to `https://api.mnemom.ai/mcp?profile=directory`. Alternatively, use the default endpoint without the profile for the full power‑user tool surface.
Mnemom MCP Server
@mnemom
基本情報
Mnemom MCP Server について
Trust ratings for AI agents and websites. Look up an agent's reputation, scan a site's AI-trust-readiness, and verify signed scorecards in-band — reads are zero-auth. From Mnemom, the trust layer for the agent internet.
Mnemom MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mnemom": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.mnemom.ai/mcp?profile=directory"
]
}
}
}Mnemom MCP Server のツール
15Claim a verifiable identity — bind an agent to your organization so its trust and accountability record is provably yours. No human in the loop.
Look up an agent's public identity and trust state by ID — the accountable record other agents and humans can rely on.
Look up an AI agent's published Trust Rating — Mnemom's portable reliability signal for autonomous software, computed from the agent's own verified activity record. Returns the rating plus the technical factors behind it. Free, public, read-only: every registered agent's rating is published by standard (the `visibility` field is the reputation-publication axis, distinct from identity-record visibility).
Get an embeddable Trust Rating badge for an agent — returns the badge image URL plus ready-to-paste Markdown and HTML snippets for a README or agent card.
Zero-auth, no-args orientation: who Mnemom is, the surface map, how to authenticate and what it unlocks, and the value tools to try right now (headlining scan_trust + the reputation reads).
List your agents — List all agents owned by the authenticated user. Supports pagination.
Preview composed alignment (dry run) — Composes the cascade against a hypothetical body at the agent layer and returns conflicts + the composed view. No DB writes. Used by the dashboard editor for live conflict markers.
Preview composed protection (dry run) — Composes the cascade against a hypothetical body at the agent layer and returns conflicts + the composed view. No DB writes. Used by the dashboard editor for live conflict markers.
Publish or replace the alignment manifest — Accepts YAML (`text/yaml`, `application/yaml`) or JSON. Body is the full `UnifiedAlignmentCard`; server-side composition merges it across the platform → org → team → agent cascade and writes the canonical composed card. Requires `Idempotency-Key`. Honor...
Publish or replace the protection manifest — Accepts YAML (`text/yaml`, `application/yaml`) or JSON. Body is the full `UnifiedProtectionCard`; server-side composition merges it across the platform → org → team → agent cascade and writes the canonical composed card. Requires `Idempotency-Key`. Hon...
Submit a false-positive / false-negative correction for one of Mnemom's automated detection rules (a 'recipe') — technical feedback that improves detection accuracy, like filing a bug report against a spam filter.
Scan a website's agent-trust-readiness and return a signed scorecard (Trust, plus an Access axis on newer rubrics). Zero-auth. Results are CACHED for up to 24h — check `cached` and `scannedAt` on the result; pass `fresh: true` to force a re-scan (rate-limited). Proxies to the SSRF-locked isittrustready scanner; the Ed25519 signature + permalink are preserved verbatim. Rubric + docs: https://www.isittrustready.ai/rubric and https://docs.mnemom.ai/.
Resolve an agent name or id-prefix to a real agent_id over the PUBLIC reputation directory (only agents whose reputation visibility is public). Zero-auth. The arriving-agent entry point: discover a concrete agent_id, then call get_reputation / verify_reputation on it.
Attest an agent's Trust Rating — returns a Merkle-root + hash-chain attestation (hash_chain_valid) proving the rating derives from an unbroken, append-only checkpoint chain, plus a pointer to the signed integrity certificate. This is a chain-integrity attestation, NOT an in-band Ed25519 signature check (that parity is verify_scan, for website scorecards).
Verify a website scan scorecard's Ed25519 signature IN-BAND (verify, don't trust). Pass a `scan` (a scorecard from scan_trust) or a `url` to re-scan; returns {verified, key_id, canonicalization} checked against the public key at mnemom://iitr/jwks. Zero-auth. Spec + rubric: https://www.isittrustready.ai/rubric and https://docs.mnemom.ai/.
概要
What is Mnemom?
Mnemom is a Model Context Protocol (MCP) server that provides trust infrastructure for the agent internet. It lets you look up a verifiable Trust Rating for an AI agent, scan a website's AI-trust-readiness, verify signed scorecards in‑band, claim an agent identity, and publish an alignment card.
How to use Mnemom?
Connect a compliant MCP client (Claude, ChatGPT, etc.) to the Streamable‑HTTP endpoint https://api.mnemom.ai/mcp?profile=directory. Reads are anonymous and require no authentication; write operations (claiming an agent, publishing an alignment card) require OAuth 2.0 with Dynamic Client Registration + PKCE or an X-Mnemom-Api-Key header.
Key features of Mnemom
- 15 curated tools across reputation, scanning, identity, and orientation groups
- Ed25519‑signed scorecards verifiable in‑band or with the published JWKS
- Zero‑auth reads – no key or login needed for lookups
- OAuth 2.0 with Dynamic Client Registration + PKCE for writes
- Website trust readiness scanning via the
scan_trusttool - Agent identity claiming and alignment card publishing
Use cases of Mnemom
- Look up a verifiable trust rating for any AI agent
- Scan a website to assess its AI‑trust readiness
- Verify an Ed25519‑signed scorecard on‑chain
- Claim an agent identity and publish an alignment declaration
- Search the reputation directory for trusted agents
よくある質問
Do I need authentication to read data?
No, reads are anonymous. You can list tools and call reputation, search, scan, verify, and get‑started tools without any account or API key.
How are scorecards verified?
Scorecards carry a self‑describing `verification` block (algorithm, key ID, canonicalization rule). You can verify a scorecard in‑band using the `verify_scan` tool, or independently check the signature against the published scanner JWKS at `mnemom://iitr/jwks`.
What authentication methods are supported for writes?
Writes require either OAuth 2.0 (with Dynamic Client Registration and PKCE) or an `X-Mnemom-Api-Key` header. A failed write returns a `401` with a `WWW-Authenticate` header pointing to the Protected Resource Metadata for automatic client configuration.
Which tools are included in the directory profile?
The curated profile exposes 15 tools across four groups: reputation (`get_reputation`, `get_reputation_badge`, `get_risk_history`, `search_reputation_directory`, `verify_reputation`, `list_agents`, `get_agent`), website trust scanning (`scan_trust`, `verify_scan`), identity & declarations (`claim_agent`, `preview_compose_alignment_by_agent`, `put_alignment_by_agent`, `report_recipe_fn_fp`), and orientation (`get_started`).
「その他」の他のコンテンツ
EverArt
modelcontextprotocolModel Context Protocol Servers
88.1K
Handl
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
26.0K
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
16.7K
Health by Dr Brad
Dr Brad StanfieldHealth by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
コメント